
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
import numpy as np # linear algebra
import seaborn as sns
import matplotlib.pyplot as plt
%matplotlib inline

# Import statements required for Plotly 
import plotly.offline as py
py.init_notebook_mode(connected=True)
import plotly.graph_objs as go
import plotly.tools as tls


from sklearn.ensemble import RandomForestClassifier, GradientBoostingClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import (accuracy_score, log_loss, classification_report)
from imblearn.over_sampling import SMOTE
import xgboost

# Import and suppress warnings
import warnings
warnings.filterwarnings('ignore')


df = pd.read_csv(r'C:\Users\Admin\Desktop\IBM\Data\WA_Fn-UseC_-HR-Employee-Attrition.csv')


df.head().style.set_properties(**{'background-color': '#E9F6E2','color': 'black','border-color': '#8b8c8c'})


df.shape

(1470, 35)


df.info(verbose=False)

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1470 entries, 0 to 1469
Columns: 35 entries, Age to YearsWithCurrManager
dtypes: int64(26), object(9)
memory usage: 402.1+ KB


df.select_dtypes(np.number).sample(5).style.set_properties(**{'background-color': '#E9F6E2',
                                                              'color': 'black','border-color': '#8b8c8c'})


df["Education"] = df["Education"].replace({1:"Below College",2:"College",3:"Bachelor",4:"Master",5:"Doctor"})

False

Unique values of  Attrition {'Yes', 'No'}
-------------------------------------------------------------------------------------------------------------------------------
Unique values of  BusinessTravel {'Travel_Frequently', 'Non-Travel', 'Travel_Rarely'}
-------------------------------------------------------------------------------------------------------------------------------
Unique values of  Department {'Human Resources', 'Sales', 'Research & Development'}
-------------------------------------------------------------------------------------------------------------------------------
Unique values of  Education {'Bachelor', 'Doctor', 'Below College', 'Master', 'College'}
-------------------------------------------------------------------------------------------------------------------------------
Unique values of  EducationField {'Technical Degree', 'Human Resources', 'Life Sciences', 'Marketing', 'Other', 'Medical'}
-------------------------------------------------------------------------------------------------------------------------------
Unique values of  EnvironmentSatisfaction {'Low', 'Medium', 'High', 'Very High'}
-------------------------------------------------------------------------------------------------------------------------------
Unique values of  Gender {'Female', 'Male'}
-------------------------------------------------------------------------------------------------------------------------------
Unique values of  JobInvolvement {'Low', 'Medium', 'High', 'Very High'}
-------------------------------------------------------------------------------------------------------------------------------
Unique values of  JobLevel {'Entry Level', 'Junior Level', 'Mid Level', 'Executive Level', 'Senior Level'}
-------------------------------------------------------------------------------------------------------------------------------
Unique values of  JobRole {'Sales Executive', 'Research Director', 'Human Resources', 'Manufacturing Director', 'Manager', 'Laboratory Technician', 'Research Scientist', 'Healthcare Representative', 'Sales Representative'}
-------------------------------------------------------------------------------------------------------------------------------
Unique values of  JobSatisfaction {'Low', 'Very High', 'High', 'Medium'}
-------------------------------------------------------------------------------------------------------------------------------
Unique values of  MaritalStatus {'Married', 'Single', 'Divorced'}
-------------------------------------------------------------------------------------------------------------------------------
Unique values of  OverTime {'Yes', 'No'}
-------------------------------------------------------------------------------------------------------------------------------
Unique values of  PerformanceRating {'Outstanding', 'Excellent'}
-------------------------------------------------------------------------------------------------------------------------------
Unique values of  RelationshipSatisfaction {'Low', 'Very High', 'High', 'Medium'}
-------------------------------------------------------------------------------------------------------------------------------
Unique values of  WorkLifeBalance {'Better', 'Bad', 'Best', 'Good'}
-------------------------------------------------------------------------------------------------------------------------------

0    2012
1    2008
2    2018
3    2010
4    2016
Name: Fecha, dtype: int64

Summarize dataset:   0%|          | 0/5 [00:00<?, ?it/s]

Generate report structure:   0%|          | 0/1 [00:00<?, ?it/s]

Render HTML:   0%|          | 0/1 [00:00<?, ?it/s]

Forma de X_train: (1176, 31)
Forma de X_test: (294, 31)
Forma de y_train: (1176,)
Forma de y_test: (294,)

Precisión del modelo: 87.41%

Matriz de Confusión:
[[241  14]
 [ 23  16]]

Precisión del modelo: 53.33%


df["Education"] = df["Education"].replace({1:"Below College",2:"College",3:"Bachelor",4:"Master",5:"Doctor"})


df["EnvironmentSatisfaction"] = df["EnvironmentSatisfaction"].replace({1:"Low",2:"Medium",3:"High",4:"Very High"})


df["JobInvolvement"] = df["JobInvolvement"].replace({1:"Low",2:"Medium",3:"High",4:"Very High"})


df["JobLevel"] = df["JobLevel"].replace({1:"Entry Level",2:"Junior Level",3:"Mid Level",4:"Senior Level",
                                         5:"Executive Level"})


df["JobSatisfaction"] = df["JobSatisfaction"].replace({1:"Low",2:"Medium",3:"High",4:"Very High"})


df["PerformanceRating"] = df["PerformanceRating"].replace({1:"Low",2:"Good",3:"Excellent",4:"Outstanding"})


df["RelationshipSatisfaction"] = df["RelationshipSatisfaction"].replace({1:"Low",2:"Medium",3:"High",4:"Very High"})


df["WorkLifeBalance"] = df["WorkLifeBalance"].replace({1:"Bad",2:"Good",3:"Better",4:"Best"})


df.select_dtypes(include="O").sample(5).style.set_properties(**{'background-color': '#E9F6E2',
                                                                'color': 'black','border-color': '#8b8c8c'})


have_duplicate_rows = df.duplicated().any()
have_duplicate_rows

False


missing_df = df.isnull().sum().to_frame().rename(columns={0:"Total No. of Missing Values"})
missing_df["% of Missing Values"] = round((missing_df["Total No. of Missing Values"]/len(df))*100,2)
missing_df


df.describe().T


cols = ["Over18","EmployeeCount","EmployeeNumber","StandardHours"]

df.drop(columns=cols, inplace=True)


df.describe(include="O").T


cat_cols = df.select_dtypes(include="O").columns

for column in cat_cols:
    print('Unique values of ', column, set(df[column]))
    print("-"*127)

Unique values of  Attrition {'Yes', 'No'}
-------------------------------------------------------------------------------------------------------------------------------
Unique values of  BusinessTravel {'Travel_Frequently', 'Non-Travel', 'Travel_Rarely'}
-------------------------------------------------------------------------------------------------------------------------------
Unique values of  Department {'Human Resources', 'Sales', 'Research & Development'}
-------------------------------------------------------------------------------------------------------------------------------
Unique values of  Education {'Bachelor', 'Doctor', 'Below College', 'Master', 'College'}
-------------------------------------------------------------------------------------------------------------------------------
Unique values of  EducationField {'Technical Degree', 'Human Resources', 'Life Sciences', 'Marketing', 'Other', 'Medical'}
-------------------------------------------------------------------------------------------------------------------------------
Unique values of  EnvironmentSatisfaction {'Low', 'Medium', 'High', 'Very High'}
-------------------------------------------------------------------------------------------------------------------------------
Unique values of  Gender {'Female', 'Male'}
-------------------------------------------------------------------------------------------------------------------------------
Unique values of  JobInvolvement {'Low', 'Medium', 'High', 'Very High'}
-------------------------------------------------------------------------------------------------------------------------------
Unique values of  JobLevel {'Entry Level', 'Junior Level', 'Mid Level', 'Executive Level', 'Senior Level'}
-------------------------------------------------------------------------------------------------------------------------------
Unique values of  JobRole {'Sales Executive', 'Research Director', 'Human Resources', 'Manufacturing Director', 'Manager', 'Laboratory Technician', 'Research Scientist', 'Healthcare Representative', 'Sales Representative'}
-------------------------------------------------------------------------------------------------------------------------------
Unique values of  JobSatisfaction {'Low', 'Very High', 'High', 'Medium'}
-------------------------------------------------------------------------------------------------------------------------------
Unique values of  MaritalStatus {'Married', 'Single', 'Divorced'}
-------------------------------------------------------------------------------------------------------------------------------
Unique values of  OverTime {'Yes', 'No'}
-------------------------------------------------------------------------------------------------------------------------------
Unique values of  PerformanceRating {'Outstanding', 'Excellent'}
-------------------------------------------------------------------------------------------------------------------------------
Unique values of  RelationshipSatisfaction {'Low', 'Very High', 'High', 'Medium'}
-------------------------------------------------------------------------------------------------------------------------------
Unique values of  WorkLifeBalance {'Better', 'Bad', 'Best', 'Good'}
-------------------------------------------------------------------------------------------------------------------------------


#Visualization to show Employee Attrition in Counts.
plt.figure(figsize=(17,6))
plt.subplot(1,2,1)
attrition_rate = df["Attrition"].value_counts()
sns.barplot(x=attrition_rate.index,y=attrition_rate.values,palette=["brown","orange"])
plt.title("Employee Attrition Counts",fontweight="black",size=20,pad=20)
for i, v in enumerate(attrition_rate.values):
    plt.text(i, v, v,ha="center", fontweight='black', fontsize=14)

#Visualization to show Employee Attrition in Percentage.
plt.subplot(1,2,2)
plt.pie(attrition_rate, labels=["No","Yes"], autopct="%.2f%%", textprops={"fontweight":"black","size":15},
        colors = ["brown","orange"],explode=[0,0.1],startangle=90)
center_circle = plt.Circle((0, 0), 0.3, fc='white')
fig = plt.gcf()
fig.gca().add_artist(center_circle)
plt.title("Employee Attrition Rate",fontweight="black",size=20,pad=10)
plt.show()


import pandas as pd

# Lee el archivo CSV original
file_path = r'C:\Users\Admin\Desktop\IBM\Data\WA_Fn-UseC_-HR-Employee-Attrition.csv'
df = pd.read_csv(file_path)

# Obtén el año actual
current_year = 2018

# Calcula la columna de fecha en base a la columna YearsAtCompany
df['Fecha'] = current_year - df['YearsAtCompany']

# Guarda el DataFrame actualizado en el archivo CSV original
df.to_csv(file_path, index=False)


import pandas as pd

# Lee el archivo CSV actualizado
file_path = r'C:\Users\Admin\Desktop\IBM\Data\WA_Fn-UseC_-HR-Employee-Attrition.csv'
df = pd.read_csv(file_path)

# Visualizar la columna de fecha
print(df['Fecha'].head())

0    2012
1    2008
2    2018
3    2010
4    2016
Name: Fecha, dtype: int64


import pandas as pd
from pandas_profiling import ProfileReport
from IPython.display import HTML

# Cargar el conjunto de datos completo
df = pd.read_csv(r'C:\Users\Admin\Desktop\IBM\Data\WA_Fn-UseC_-HR-Employee-Attrition.csv')
cols = ["Over18","EmployeeCount","EmployeeNumber","StandardHours"]

df.drop(columns=cols, inplace=True)

# Generar el informe de perfilado de datos
profile = ProfileReport(df)

# Mostrar el informe en el notebook
HTML(profile.to_html())

Summarize dataset:   0%|          | 0/5 [00:00<?, ?it/s]

Generate report structure:   0%|          | 0/1 [00:00<?, ?it/s]

Render HTML:   0%|          | 0/1 [00:00<?, ?it/s]


from sklearn.model_selection import train_test_split

# Separar características (X) y etiquetas (y)
X = df.drop('Attrition', axis=1)
y = df['Attrition']

# Dividir los datos en conjuntos de entrenamiento y prueba
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Mostrar las formas de los conjuntos de datos
print("Forma de X_train:", X_train.shape)
print("Forma de X_test:", X_test.shape)
print("Forma de y_train:", y_train.shape)
print("Forma de y_test:", y_test.shape)

Forma de X_train: (1176, 31)
Forma de X_test: (294, 31)
Forma de y_train: (1176,)
Forma de y_test: (294,)


from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score
from sklearn.preprocessing import OneHotEncoder
import numpy as np


# Combinar los datos de entrenamiento y prueba
X_combined = np.vstack((X_train, X_test))

# Codificar variables categóricas usando OneHotEncoder
encoder = OneHotEncoder()
X_combined_encoded = encoder.fit_transform(X_combined)

# Dividir los datos codificados de nuevo en entrenamiento y prueba
X_train_encoded = X_combined_encoded[:X_train.shape[0]]
X_test_encoded = X_combined_encoded[X_train.shape[0]:]

# Crear una instancia del modelo de regresión logística
model = LogisticRegression()

# Entrenar el modelo con los datos de entrenamiento codificados
model.fit(X_train_encoded, y_train)

# Realizar predicciones en los datos de prueba codificados
y_pred = model.predict(X_test_encoded)

# Calcular la precisión del modelo
accuracy = accuracy_score(y_test, y_pred)

# Imprimir la precisión del modelo
print("Precisión del modelo: {:.2f}%".format(accuracy * 100))

Precisión del modelo: 87.41%


from sklearn.metrics import confusion_matrix


# Crear la matriz de confusión
confusion = confusion_matrix(y_test, y_pred)

# Imprimir la matriz de confusión
print("Matriz de Confusión:")
print(confusion)

Matriz de Confusión:
[[241  14]
 [ 23  16]]


from sklearn.metrics import precision_score
cols = ["Over18","EmployeeCount","EmployeeNumber","StandardHours"]

df.drop(columns=cols, inplace=True)

# Calcular la precisión del modelo
precision = precision_score(y_test, y_pred, pos_label='Yes')

# Imprimir la precisión del modelo
print("Precisión del modelo: {:.2f}%".format(precision * 100))

Precisión del modelo: 53.33%


import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score

# Cargar los datos
data = pd.read_csv(r'C:\Users\Admin\Desktop\IBM\Data\WA_Fn-UseC_-HR-Employee-Attrition.csv')
cols = ["Over18","EmployeeCount","EmployeeNumber","StandardHours"]

df.drop(columns=cols, inplace=True)

# Preprocesar los datos
le = LabelEncoder()
data['Attrition'] = le.fit_transform(data['Attrition'])
data = pd.get_dummies(data)

# Dividir los datos en conjunto de entrenamiento y prueba
X = data.drop('Attrition', axis=1)
y = data['Attrition']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Entrenar el modelo de Random Forest
model = RandomForestClassifier(random_state=42)
model.fit(X_train, y_train)

# Hacer predicciones en el conjunto de prueba
y_pred = model.predict(X_test)

# Calcular las métricas de evaluación
accuracy = accuracy_score(y_test, y_pred)
precision = precision_score(y_test, y_pred)
recall = recall_score(y_test, y_pred)
f1 = f1_score(y_test, y_pred)

# Imprimir las métricas
print('Accuracy:', accuracy)
print('Precision:', precision)
print('Recall:', recall)
print('F1 Score:', f1)

Accuracy: 0.8775510204081632
Precision: 0.7142857142857143
Recall: 0.1282051282051282
F1 Score: 0.21739130434782608


import pandas as pd

# Cargar el archivo CSV en un dataframe
data = pd.read_csv(r'C:\Users\Admin\Desktop\IBM\Data\WA_Fn-UseC_-HR-Employee-Attrition.csv')

# Convertir la columna 'Attrition' en valores numéricos (1 para 'Yes' y 0 para 'No')
df['Attrition'] = df['Attrition'].apply(lambda x: 1 if x == 'Yes' else 0)

# Verificar los primeros registros de la columna 'Attrition' convertida
print(df['Attrition'].head())

0    0
1    0
2    0
3    0
4    0
Name: Attrition, dtype: int64


df.head().T


import pandas as pd

data = pd.read_csv(r'C:\Users\Admin\Desktop\IBM\Data\WA_Fn-UseC_-HR-Employee-Attrition.csv')

# Convertir la columna 'Attrition' en valores binarios (1 para 'Sí' y 0 para 'No')
df['Attrition'] = df['Attrition'].map({'Yes': 1, 'No': 0})

# Calcular la matriz de correlación utilizando el método Pearson
corr_p = df.corr()

# Calcular la matriz de correlación utilizando el método Kendall
corr_k = df.corr(method='kendall')

# Calcular la matriz de correlación utilizando el método Spearman
corr_s = df.corr(method='spearman')

# Imprimir la matriz de correlación con el método Spearman
print(corr_s)

                               Age  Attrition  DailyRate  DistanceFromHome  \
Age                       1.000000        NaN   0.007290         -0.019291   
Attrition                      NaN        NaN        NaN               NaN   
DailyRate                 0.007290        NaN   1.000000         -0.002754   
DistanceFromHome         -0.019291        NaN  -0.002754          1.000000   
Education                 0.204937        NaN  -0.013607          0.015708   
EmployeeCount                  NaN        NaN        NaN               NaN   
EmployeeNumber           -0.001770        NaN  -0.051800          0.038906   
EnvironmentSatisfaction   0.009820        NaN   0.018961         -0.010401   
HourlyRate                0.028858        NaN   0.023511          0.020446   
JobInvolvement            0.034456        NaN   0.042469          0.034430   
JobLevel                  0.489618        NaN   0.003816          0.022148   
JobSatisfaction          -0.005185        NaN   0.027829         -0.013078   
MonthlyIncome             0.471902        NaN   0.016260          0.002512   
MonthlyRate               0.017451        NaN  -0.032360          0.039618   
NumCompaniesWorked        0.353213        NaN   0.036548         -0.009592   
PercentSalaryHike         0.007709        NaN   0.025070          0.029666   
PerformanceRating         0.000093        NaN   0.000624          0.011320   
RelationshipSatisfaction  0.046063        NaN   0.009685          0.005852   
StandardHours                  NaN        NaN        NaN               NaN   
StockOptionLevel          0.056633        NaN   0.038514          0.030190   
TotalWorkingYears         0.656896        NaN   0.020951         -0.002912   
TrainingTimesLastYear     0.000316        NaN  -0.011339         -0.024848   
WorkLifeBalance          -0.003707        NaN  -0.040352         -0.020402   
YearsAtCompany            0.251686        NaN  -0.009778          0.010513   
YearsInCurrentRole        0.197978        NaN   0.007208          0.013708   
YearsSinceLastPromotion   0.173647        NaN  -0.037631         -0.004685   
YearsWithCurrManager      0.194818        NaN  -0.004717          0.004448   
Fecha                    -0.251686        NaN   0.009778         -0.010513   

                          Education  EmployeeCount  EmployeeNumber  \
Age                        0.204937            NaN       -0.001770   
Attrition                       NaN            NaN             NaN   
DailyRate                 -0.013607            NaN       -0.051800   
DistanceFromHome           0.015708            NaN        0.038906   
Education                  1.000000            NaN        0.042815   
EmployeeCount                   NaN            NaN             NaN   
EmployeeNumber             0.042815            NaN        1.000000   
EnvironmentSatisfaction   -0.027625            NaN        0.021750   
HourlyRate                 0.014432            NaN        0.034717   
JobInvolvement             0.037231            NaN       -0.002453   
JobLevel                   0.107419            NaN       -0.011057   
JobSatisfaction           -0.005175            NaN       -0.047150   
MonthlyIncome              0.120028            NaN        0.001797   
MonthlyRate               -0.021214            NaN        0.011933   
NumCompaniesWorked         0.135103            NaN        0.007011   
PercentSalaryHike          0.004300            NaN       -0.008179   
PerformanceRating         -0.025081            NaN       -0.020675   
RelationshipSatisfaction  -0.013173            NaN       -0.072991   
StandardHours                   NaN            NaN             NaN   
StockOptionLevel           0.013794            NaN        0.059480   
TotalWorkingYears          0.162177            NaN       -0.003748   
TrainingTimesLastYear     -0.023749            NaN        0.026502   
WorkLifeBalance            0.017350            NaN        0.009994   
YearsAtCompany             0.064196            NaN        0.013205   
YearsInCurrentRole         0.054567            NaN       -0.001079   
YearsSinceLastPromotion    0.032203            NaN        0.007857   
YearsWithCurrManager       0.051292            NaN       -0.005138   
Fecha                     -0.064196            NaN       -0.013205   

                          EnvironmentSatisfaction  HourlyRate  JobInvolvement  \
Age                                      0.009820    0.028858        0.034456   
Attrition                                     NaN         NaN             NaN   
DailyRate                                0.018961    0.023511        0.042469   
DistanceFromHome                        -0.010401    0.020446        0.034430   
Education                               -0.027625    0.014432        0.037231   
EmployeeCount                                 NaN         NaN             NaN   
EmployeeNumber                           0.021750    0.034717       -0.002453   
EnvironmentSatisfaction                  1.000000   -0.052380       -0.015301   
HourlyRate                              -0.052380    1.000000        0.043884   
JobInvolvement                          -0.015301    0.043884        1.000000   
JobLevel                                -0.000192   -0.033876       -0.018424   
JobSatisfaction                         -0.002993   -0.068340       -0.012148   
MonthlyIncome                           -0.015163   -0.019762       -0.024552   
MonthlyRate                              0.037477   -0.014888       -0.018117   
NumCompaniesWorked                       0.006151    0.019209        0.015448   
PercentSalaryHike                       -0.030489   -0.009876       -0.016999   
PerformanceRating                       -0.029160   -0.002185       -0.024733   
RelationshipSatisfaction                 0.005353    0.000259        0.037857   
StandardHours                                 NaN         NaN             NaN   
StockOptionLevel                         0.009826    0.050543        0.034464   
TotalWorkingYears                       -0.013882   -0.012072        0.006444   
TrainingTimesLastYear                   -0.011659    0.000292        0.002014   
WorkLifeBalance                          0.027169   -0.010003       -0.019889   
YearsAtCompany                           0.008425   -0.029032        0.013836   
YearsInCurrentRole                       0.020140   -0.034016        0.015548   
YearsSinceLastPromotion                  0.026082   -0.052412       -0.008307   
YearsWithCurrManager                    -0.001732   -0.013811        0.037397   
Fecha                                   -0.008425    0.029032       -0.013836   

                          ...  StandardHours  StockOptionLevel  \
Age                       ...            NaN          0.056633   
Attrition                 ...            NaN               NaN   
DailyRate                 ...            NaN          0.038514   
DistanceFromHome          ...            NaN          0.030190   
Education                 ...            NaN          0.013794   
EmployeeCount             ...            NaN               NaN   
EmployeeNumber            ...            NaN          0.059480   
EnvironmentSatisfaction   ...            NaN          0.009826   
HourlyRate                ...            NaN          0.050543   
JobInvolvement            ...            NaN          0.034464   
JobLevel                  ...            NaN          0.047786   
JobSatisfaction           ...            NaN          0.012785   
MonthlyIncome             ...            NaN          0.045852   
MonthlyRate               ...            NaN         -0.037274   
NumCompaniesWorked        ...            NaN          0.032277   
PercentSalaryHike         ...            NaN          0.023446   
PerformanceRating         ...            NaN          0.011028   
RelationshipSatisfaction  ...            NaN         -0.056249   
StandardHours             ...            NaN               NaN   
StockOptionLevel          ...            NaN          1.000000   
TotalWorkingYears         ...            NaN          0.052618   
TrainingTimesLastYear     ...            NaN          0.003388   
WorkLifeBalance           ...            NaN         -0.016568   
YearsAtCompany            ...            NaN          0.064974   
YearsInCurrentRole        ...            NaN          0.071627   
YearsSinceLastPromotion   ...            NaN          0.027502   
YearsWithCurrManager      ...            NaN          0.053646   
Fecha                     ...            NaN         -0.064974   

                          TotalWorkingYears  TrainingTimesLastYear  \
Age                                0.656896               0.000316   
Attrition                               NaN                    NaN   
DailyRate                          0.020951              -0.011339   
DistanceFromHome                  -0.002912              -0.024848   
Education                          0.162177              -0.023749   
EmployeeCount                           NaN                    NaN   
EmployeeNumber                    -0.003748               0.026502   
EnvironmentSatisfaction           -0.013882              -0.011659   
HourlyRate                        -0.012072               0.000292   
JobInvolvement                     0.006444               0.002014   
JobLevel                           0.734678              -0.019729   
JobSatisfaction                   -0.015875              -0.011681   
MonthlyIncome                      0.710024              -0.034847   
MonthlyRate                        0.013360              -0.010018   
NumCompaniesWorked                 0.315196              -0.047336   
PercentSalaryHike                 -0.025528              -0.004106   
PerformanceRating                  0.011678              -0.016676   
RelationshipSatisfaction           0.003971               0.005424   
StandardHours                           NaN                    NaN   
StockOptionLevel                   0.052618               0.003388   
TotalWorkingYears                  1.000000              -0.014151   
TrainingTimesLastYear             -0.014151               1.000000   
WorkLifeBalance                    0.003004               0.023690   
YearsAtCompany                     0.594193               0.001389   
YearsInCurrentRole                 0.492721               0.004581   
YearsSinceLastPromotion            0.334996               0.010215   
YearsWithCurrManager               0.495254              -0.011628   
Fecha                             -0.594193              -0.001389   

                          WorkLifeBalance  YearsAtCompany  YearsInCurrentRole  \
Age                             -0.003707        0.251686            0.197978   
Attrition                             NaN             NaN                 NaN   
DailyRate                       -0.040352       -0.009778            0.007208   
DistanceFromHome                -0.020402        0.010513            0.013708   
Education                        0.017350        0.064196            0.054567   
EmployeeCount                         NaN             NaN                 NaN   
EmployeeNumber                   0.009994        0.013205           -0.001079   
EnvironmentSatisfaction          0.027169        0.008425            0.020140   
HourlyRate                      -0.010003       -0.029032           -0.034016   
JobInvolvement                  -0.019889        0.013836            0.015548   
JobLevel                         0.040466        0.472283            0.391085   
JobSatisfaction                 -0.029781        0.012280            0.000531   
MonthlyIncome                    0.030759        0.464315            0.394712   
MonthlyRate                      0.006316       -0.029862           -0.006865   
NumCompaniesWorked               0.009103       -0.171070           -0.127673   
PercentSalaryHike                0.000930       -0.054117           -0.025528   
PerformanceRating                0.006808        0.017224            0.032719   
RelationshipSatisfaction         0.017684       -0.001267           -0.021400   
StandardHours                         NaN             NaN                 NaN   
StockOptionLevel                -0.016568        0.064974            0.071627   
TotalWorkingYears                0.003004        0.594193            0.492721   
TrainingTimesLastYear            0.023690        0.001389            0.004581   
WorkLifeBalance                  1.000000        0.004675            0.023214   
YearsAtCompany                   0.004675        1.000000            0.854000   
YearsInCurrentRole               0.023214        0.854000            1.000000   
YearsSinceLastPromotion          0.002151        0.519966            0.505657   
YearsWithCurrManager            -0.004591        0.842803            0.724754   
Fecha                           -0.004675       -1.000000           -0.854000   

                          YearsSinceLastPromotion  YearsWithCurrManager  \
Age                                      0.173647              0.194818   
Attrition                                     NaN                   NaN   
DailyRate                               -0.037631             -0.004717   
DistanceFromHome                        -0.004685              0.004448   
Education                                0.032203              0.051292   
EmployeeCount                                 NaN                   NaN   
EmployeeNumber                           0.007857             -0.005138   
EnvironmentSatisfaction                  0.026082             -0.001732   
HourlyRate                              -0.052412             -0.013811   
JobInvolvement                          -0.008307              0.037397   
JobLevel                                 0.269096              0.370889   
JobSatisfaction                          0.007497             -0.016772   
MonthlyIncome                            0.264599              0.365386   
MonthlyRate                             -0.016285             -0.035059   
NumCompaniesWorked                      -0.066950             -0.144129   
PercentSalaryHike                       -0.055362             -0.026049   
PerformanceRating                       -0.006578              0.025560   
RelationshipSatisfaction                 0.036963              0.000280   
StandardHours                                 NaN                   NaN   
StockOptionLevel                         0.027502              0.053646   
TotalWorkingYears                        0.334996              0.495254   
TrainingTimesLastYear                    0.010215             -0.011628   
WorkLifeBalance                          0.002151             -0.004591   
YearsAtCompany                           0.519966              0.842803   
YearsInCurrentRole                       0.505657              0.724754   
YearsSinceLastPromotion                  1.000000              0.466713   
YearsWithCurrManager                     0.466713              1.000000   
Fecha                                   -0.519966             -0.842803   

                             Fecha  
Age                      -0.251686  
Attrition                      NaN  
DailyRate                 0.009778  
DistanceFromHome         -0.010513  
Education                -0.064196  
EmployeeCount                  NaN  
EmployeeNumber           -0.013205  
EnvironmentSatisfaction  -0.008425  
HourlyRate                0.029032  
JobInvolvement           -0.013836  
JobLevel                 -0.472283  
JobSatisfaction          -0.012280  
MonthlyIncome            -0.464315  
MonthlyRate               0.029862  
NumCompaniesWorked        0.171070  
PercentSalaryHike         0.054117  
PerformanceRating        -0.017224  
RelationshipSatisfaction  0.001267  
StandardHours                  NaN  
StockOptionLevel         -0.064974  
TotalWorkingYears        -0.594193  
TrainingTimesLastYear    -0.001389  
WorkLifeBalance          -0.004675  
YearsAtCompany           -1.000000  
YearsInCurrentRole       -0.854000  
YearsSinceLastPromotion  -0.519966  
YearsWithCurrManager     -0.842803  
Fecha                     1.000000  

[28 rows x 28 columns]


import pandas as pd

df = pd.read_csv(r'C:\Users\Admin\Desktop\IBM\Data\WA_Fn-UseC_-HR-Employee-Attrition.csv')

# Convertir la columna 'Attrition' en valores binarios (1 para 'Sí' y 0 para 'No')
df['Attrition'] = df['Attrition'].map({'Yes': 1, 'No': 0})

# Calcular la matriz de correlación utilizando el método Pearson
corr_p = df.corr()

# Obtener las correlaciones absolutas con 'Attrition' y ordenar de forma descendente
corr_abs = corr_p['Attrition'].abs().sort_values(ascending=False)

# Imprimir las correlaciones absolutas
print(corr_abs)

Attrition                   1.000000
TotalWorkingYears           0.171063
JobLevel                    0.169105
YearsInCurrentRole          0.160545
MonthlyIncome               0.159840
Age                         0.159205
YearsWithCurrManager        0.156199
StockOptionLevel            0.137145
YearsAtCompany              0.134392
Fecha                       0.134392
JobInvolvement              0.130016
JobSatisfaction             0.103481
EnvironmentSatisfaction     0.103369
DistanceFromHome            0.077924
WorkLifeBalance             0.063939
TrainingTimesLastYear       0.059478
DailyRate                   0.056652
RelationshipSatisfaction    0.045872
NumCompaniesWorked          0.043494
YearsSinceLastPromotion     0.033019
Education                   0.031373
MonthlyRate                 0.015170
PercentSalaryHike           0.013478
EmployeeNumber              0.010577
HourlyRate                  0.006846
PerformanceRating           0.002889
EmployeeCount                    NaN
StandardHours                    NaN
Name: Attrition, dtype: float64


import pandas as pd

df = pd.read_csv(r'C:\Users\Admin\Desktop\IBM\Data\WA_Fn-UseC_-HR-Employee-Attrition.csv')
# Convertir la columna 'Attrition' en valores binarios (1 para 'Sí' y 0 para 'No')
df['Attrition'] = df['Attrition'].map({'Yes': 1, 'No': 0})
corr_p = df.corr()
corr_k = df.corr(method ='kendall')
corr_s = df.corr(method ='spearman')

corr_s


import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
import seaborn as sns
df = pd.read_csv(r'C:\Users\Admin\Desktop\IBM\Data\WA_Fn-UseC_-HR-Employee-Attrition.csv')

#Visualization to show Total Employees by Gender.
plt.figure(figsize=(14,6))
plt.subplot(1,2,1)
gender_attrition = df["Gender"].value_counts()
plt.title("Employees Distribution by Gender",fontweight="black",size=20)
plt.pie(gender_attrition, autopct="%.0f%%",labels=gender_attrition.index,textprops=({"fontweight":"black","size":20}),
        explode=[0,0.1],startangle=90,colors= ["#D4A1E7","brown"])


#Visualization to show Employee Attrition by Gender.
plt.subplot(1,2,2)
new_df = df[df["Attrition"]=="Yes"]
value_1 = df["Gender"].value_counts()
value_2 = new_df["Gender"].value_counts()
attrition_rate = np.floor((value_2/value_1)*100).values
sns.barplot(x=value_2.index, y=value_2.values,palette=["#D4A1E7","brown"])
plt.title("Employee Attrition Rate by Gender",fontweight="black",size=20,pad=20)
for index,value in enumerate(value_2):
    plt.text(index,value,str(value)+" ("+str(int(attrition_rate[index]))+"% )",ha="center",va="bottom",
             size=15,fontweight="black")
plt.tight_layout()
plt.show()


#Visualization to show Employee Distribution by Age.
plt.figure(figsize=(13.5,6))
plt.subplot(1,2,1)
sns.histplot(x="Age",hue="Attrition",data=df,kde=True,palette=["blue","orange"])
plt.title("Employee Distribution by Age",fontweight="black",size=20,pad=10)


#Visualization to show Employee Distribution by Age & Attrition.
plt.subplot(1,2,2)
sns.boxplot(x="Attrition",y="Age",data=df,palette=["orange","blue"])
plt.title("Employee Distribution by Age & Attrition",fontweight="black",size=20,pad=10)
plt.tight_layout()
plt.show()


#Visualization to show Total Employees by Businees Travel.
plt.figure(figsize=(14,6))
plt.subplot(1,2,1)
value_1 = df["BusinessTravel"].value_counts()
plt.title("Employees by Business Travel", fontweight="black", size=20, pad=20)
plt.pie(value_1.values, labels=value_1.index, autopct="%.1f%%",pctdistance=0.75,startangle=90,
        colors=['green', 'blue', 'brown'],textprops={"fontweight":"black","size":15})
center_circle = plt.Circle((0, 0), 0.4, fc='white')
fig = plt.gcf()
fig.gca().add_artist(center_circle)

#Visualization to show Attrition Rate by Businees Travel.
plt.subplot(1,2,2)
new_df = df[df["Attrition"]=="Yes"]
value_2 = new_df["BusinessTravel"].value_counts()
attrition_rate = np.floor((value_2/value_1)*100).values
sns.barplot(x=value_2.index,y=value_2.values,palette=["green","blue","brown"])
plt.title("Attrition Rate by Businees Travel",fontweight="black",size=20,pad=20)
for index,value in enumerate(value_2):
    plt.text(index,value,str(value)+" ("+str(int(attrition_rate[index]))+"% )",ha="center",va="bottom",
             size=15,fontweight="black")
plt.tight_layout()
plt.show()


#Visualization to show Total Employees by Department.
plt.figure(figsize=(14,6))
plt.subplot(1,2,1)
value_1 = df["Department"].value_counts()
sns.barplot(x=value_1.index, y=value_1.values,palette = ["orange", "red", "blue"])
plt.title("Employees by Department",fontweight="black",size=20,pad=20)
for index,value in enumerate(value_1.values):
    plt.text(index,value,value,ha="center",va="bottom",fontweight="black",size=15,)

#Visualization to show Employee Attrition Rate by Department.
plt.subplot(1,2,2)
new_df = df[df["Attrition"]=="Yes"]
value_2 = new_df["Department"].value_counts()
attrition_rate = np.floor((value_2/value_1)*100).values
sns.barplot(x=value_2.index, y=value_2.values,palette=["blue","orange","red"])
plt.title("Attrition Rate by Department",fontweight="black",size=20,pad=20)
for index,value in enumerate(value_2):
    plt.text(index,value,str(value)+" ("+str(attrition_rate[index])+"% )",ha="center",va="bottom",
             size=15,fontweight="black")
plt.tight_layout()
plt.show()


df["DailyRate"].describe().T

count    1470.000000
mean      802.485714
std       403.509100
min       102.000000
25%       465.000000
50%       802.000000
75%      1157.000000
max      1499.000000
Name: DailyRate, dtype: float64


# Define the bin edges for the groups
bin_edges = [0, 500, 1000, 1500]

# Define the labels for the groups
bin_labels = ['Low DailyRate', 'Average DailyRate', 'High DailyRate']

# Cut the DailyRate column into groups
df['DailyRateGroup'] = pd.cut(df['DailyRate'], bins=bin_edges, labels=bin_labels)


##Visualization to show Total Employees by DailyRateGroup.
plt.figure(figsize=(13,6))
plt.subplot(1,2,1)
value_1 = df["DailyRateGroup"].value_counts()
plt.pie(value_1.values, labels=value_1.index,autopct="%.2f%%",textprops={"fontweight":"black","size":15},
        explode=[0,0.1,0.1],colors= ['#FF8000', 'blue', 'brown', 'orange'])
plt.title("Employees by DailyRateGroup",fontweight="black",pad=15,size=18)


#Visualization to show Attrition Rate by DailyRateGroup.
plt.subplot(1,2,2)
new_df = df[df["Attrition"]=="Yes"]
value_2 = new_df["DailyRateGroup"].value_counts()
attrition_rate = np.floor((value_2/value_1)*100).values
sns.barplot(x=value_2.index.tolist(),y= value_2.values,palette=["#11264e","#6faea4","#FEE08B"])
plt.title("Employee Attrition Rate by DailyRateGroup",fontweight="black",pad=15,size=18)
for index,value in enumerate(value_2.values):
    plt.text(index,value, str(value)+" ("+str(attrition_rate[index])+"%)",ha="center",va="bottom",fontweight="black",size=15)

plt.tight_layout()
plt.show()


print("Total Unique Values in Attribute is =>",df["DistanceFromHome"].nunique())

Total Unique Values in Attribute is => 29


df["DistanceFromHome"].describe().T

count    1470.000000
mean        9.192517
std         8.106864
min         1.000000
25%         2.000000
50%         7.000000
75%        14.000000
max        29.000000
Name: DistanceFromHome, dtype: float64


# Define the bin edges for the groups
bin_edges = [0,2,5,10,30]

# Define the labels for the groups
bin_labels = ['0-2 kms', '3-5 kms', '6-10 kms',"10+ kms"]

# Cuttinf the DistaanceFromHome column into groups
df['DistanceGroup'] = pd.cut(df['DistanceFromHome'], bins=bin_edges, labels=bin_labels)


##Visualization to show Total Employees by DistnaceFromHome.
plt.figure(figsize=(14,6))
plt.subplot(1,2,1)
value_1 = df["DistanceGroup"].value_counts()
sns.barplot(x=value_1.index.tolist(), y=value_1.values,palette = ["blue", "orange", "green","#87CEFA"])
plt.title("Employees by Distance From Home",fontweight="black",pad=15,size=18)
for index, value in enumerate(value_1.values):
    plt.text(index,value,value,ha="center",va="bottom",fontweight="black",size=15)
    
#Visualization to show Attrition Rate by DistanceFromHome.
plt.subplot(1,2,2)
new_df = df[df["Attrition"]=="Yes"]
value_2 = new_df["DistanceGroup"].value_counts()
attrition_rate = np.floor((value_2/value_1)*100).values
sns.barplot(x=value_2.index.tolist(),y= value_2.values,palette=["#11264e","#6faea4","#FEE08B","#D4A1E7","#E7A1A1"])
plt.title("Attrition Rate by DistanceFromHome",fontweight="black",pad=15,size=18)
for index,value in enumerate(value_2.values):
    plt.text(index,value, str(value)+" ("+str(attrition_rate[index])+"%)",ha="center",va="bottom",fontweight="black",size=15)

plt.tight_layout()
plt.show()


#Visualization to show Total Employees by Education.
plt.figure(figsize=(13.5,6))
plt.subplot(1,2,1)
value_1 = df["Education"].value_counts()
sns.barplot(x=value_1.index,y=value_1.values,order=value_1.index,palette = ["#FFA07A", "#D4A1E7", "#FFC0CB","#87CEFA"])
plt.title("Employees Distribution by Education",fontweight="black",size=20,pad=15)
for index,value in enumerate(value_1.values):
    plt.text(index,value,value,ha="center",va="bottom",fontweight="black",size=15)
    
#Visualization to show Employee Attrition by Education.
plt.subplot(1,2,2)
value_2 = new_df["Education"].value_counts()
attrition_rate = np.floor((value_2/value_1)*100).values
sns.barplot(x=value_2.index,y=value_2.values,order=value_2.index,palette=["#11264e","#6faea4","#FEE08B","#D4A1E7","#E7A1A1"])
plt.title("Employee Attrition by Education",fontweight="black",size=18,pad=15)
for index,value in enumerate(value_2.values):
    plt.text(index,value,str(value)+" ("+str(attrition_rate[index])+"%)",ha="center",va="bottom",
             fontweight="black",size=13)
plt.tight_layout()
plt.show()


#Visualization to show Total Employees by Education Field.
plt.figure(figsize=(13.5,8))
plt.subplot(1,2,1)
value_1 = df["EducationField"].value_counts()
sns.barplot(x=value_1.index, y=value_1.values,order=value_1.index,palette = ["yellow", "blue", "green","brown"])
plt.title("Employees by Education Field",fontweight="black",size=20,pad=15)
for index,value in enumerate(value_1.values):
    plt.text(index,value,value,ha="center",va="bottom",fontweight="black",size=15)
plt.xticks(rotation=90)

#Visualization to show Employee Attrition by Education Field.
plt.subplot(1,2,2)
value_2 = new_df["EducationField"].value_counts()
attrition_rate = np.floor((value_2/value_1)*100).values
sns.barplot(x=value_2.index,y=value_2.values,order=value_2.index,palette=["blue","yellow","brown","orange"])
plt.title("Employee Attrition by Education Field",fontweight="black",size=18,pad=15)
for index,value in enumerate(value_2.values):
    plt.text(index,value,str(value)+" ("+str(attrition_rate[index])+"%)",ha="center",va="bottom",
             fontweight="black",size=13)
plt.xticks(rotation=90)
plt.tight_layout()
plt.show()


#Visualization to show Total Employees by EnvironmentSatisfaction.
plt.figure(figsize=(14,6))
plt.subplot(1,2,1)
value_1 = df["EnvironmentSatisfaction"].value_counts()
plt.title("Employees by EnvironmentSatisfaction", fontweight="black", size=20, pad=20)
plt.pie(value_1.values, labels=value_1.index, autopct="%.1f%%",pctdistance=0.75,startangle=90,
        colors=['#E84040', '#E96060', '#E88181'],textprops={"fontweight":"black","size":15})
center_circle = plt.Circle((0, 0), 0.4, fc='white')
fig = plt.gcf()
fig.gca().add_artist(center_circle)

    
#Visualization to show Attrition Rate by EnvironmentSatisfaction.
plt.subplot(1,2,2)
new_df = df[df["Attrition"]=="Yes"]
value_2 = new_df["EnvironmentSatisfaction"].value_counts()
attrition_rate = np.floor((value_2/value_1)*100).values
sns.barplot(x=value_2.index,y=value_2.values,order=value_2.index,palette=["#11264e","#6faea4","#FEE08B","#D4A1E7","#E7A1A1"])
plt.title("Attrition Rate by Environment Satisfaction",fontweight="black",size=20,pad=20)
for index,value in enumerate(value_2):
    plt.text(index,value,str(value)+" ("+str(attrition_rate[index])+"% )",ha="center",va="bottom",
             size=15,fontweight="black")
plt.tight_layout()
plt.show()


##Visualization to show Total Employees by JobRole.
plt.figure(figsize=(13,8))
plt.subplot(1,2,1)
value_1 = df["JobRole"].value_counts()
sns.barplot(x=value_1.index.tolist(), y=value_1.values,palette = ["#FFA07A", "#D4A1E7", "#FFC0CB","#87CEFA"])
plt.title("Employees by Job Role",fontweight="black",pad=15,size=18)
plt.xticks(rotation=90)
for index, value in enumerate(value_1.values):
    plt.text(index,value,value,ha="center",va="bottom",fontweight="black",size=15)
    
#Visualization to show Attrition Rate by JobRole.
plt.subplot(1,2,2)
new_df = df[df["Attrition"]=="Yes"]
value_2 = new_df["JobRole"].value_counts()
attrition_rate = np.floor((value_2/value_1)*100).values
sns.barplot(x=value_2.index.tolist(), y=value_2.values,palette=["#11264e","#6faea4","#FEE08B","#D4A1E7","#E7A1A1"])
plt.title("Employee Attrition Rate by JobRole",fontweight="black",pad=15,size=18)
plt.xticks(rotation=90)
for index,value in enumerate(value_2.values):
    plt.text(index,value, str(value)+" ("+str(int(attrition_rate[index]))+"%)",ha="center",va="bottom",
             fontweight="black",size=10)

plt.tight_layout()
plt.show()


#Visualization to show Total Employees by Job Level.
plt.figure(figsize=(14,6))
plt.subplot(1,2,1)
value_1 = df["JobLevel"].value_counts()
plt.title("Employees by Job Level", fontweight="black", size=20, pad=20)
plt.pie(value_1.values, labels=value_1.index, autopct="%.1f%%",pctdistance=0.8,startangle=90,
        colors=['#FF6D8C', '#FF8C94', '#FFAC9B', '#FFCBA4',"#FFD8B1"],textprops={"fontweight":"black","size":15})
center_circle = plt.Circle((0, 0), 0.4, fc='white')
fig = plt.gcf()
fig.gca().add_artist(center_circle)

    
#Visualization to show Attrition Rate by JobLevel.
plt.subplot(1,2,2)
new_df = df[df["Attrition"]=="Yes"]
value_2 = new_df["JobLevel"].value_counts()
attrition_rate = np.floor((value_2/value_1)*100).values
sns.barplot(x=value_2.index,y=value_2.values,order=value_2.index,palette=["#11264e","#6faea4","#FEE08B","#D4A1E7","#E7A1A1"])
plt.title("Attrition Rate by Job Level",fontweight="black",size=20,pad=20)
for index,value in enumerate(value_2):
    plt.text(index,value,str(value)+" ("+str(attrition_rate[index])+"% )",ha="center",va="bottom",
             size=15,fontweight="black")
plt.tight_layout()
plt.show()


#Visualization to show Total Employees by Job Satisfaction.
plt.figure(figsize=(14,6))
plt.subplot(1,2,1)
value_1 = df["JobSatisfaction"].value_counts()
plt.title("Employees by Job Satisfaction", fontweight="black", size=20, pad=20)
plt.pie(value_1.values, labels=value_1.index, autopct="%.1f%%",pctdistance=0.8,startangle=90,
        colors=['#FFB300', '#FFC300', '#FFD700', '#FFFF00'],textprops={"fontweight":"black","size":15})
center_circle = plt.Circle((0, 0), 0.4, fc='white')
fig = plt.gcf()
fig.gca().add_artist(center_circle)

    
#Visualization to show Attrition Rate by Job Satisfaction.
plt.subplot(1,2,2)
new_df = df[df["Attrition"]=="Yes"]
value_2 = new_df["JobSatisfaction"].value_counts()
attrition_rate = np.floor((value_2/value_1)*100).values
sns.barplot(x=value_2.index,y=value_2.values,order=value_2.index,palette=["#11264e","#6faea4","#FEE08B","#D4A1E7","#E7A1A1"])
plt.title("Attrition Rate by Job Satisfaction",fontweight="black",size=20,pad=20)
for index,value in enumerate(value_2):
    plt.text(index,value,str(value)+" ("+str(attrition_rate[index])+"% )",ha="center",va="bottom",
             size=15,fontweight="black")
plt.tight_layout()
plt.show()


#Visualization to show Total Employees by MaritalStatus.
plt.figure(figsize=(14,6))
plt.subplot(1,2,1)
value_1 = df["MaritalStatus"].value_counts()
plt.title("Employees by MaritalStatus", fontweight="black", size=20, pad=20)
plt.pie(value_1.values, labels=value_1.index, autopct="%.1f%%",pctdistance=0.75,startangle=90,
        colors=['#E84040', '#E96060', '#E88181', '#E7A1A1'],textprops={"fontweight":"black","size":15})
center_circle = plt.Circle((0, 0), 0.4, fc='white')
fig = plt.gcf()
fig.gca().add_artist(center_circle)

    
#Visualization to show Attrition Rate by MaritalStatus.
plt.subplot(1,2,2)
new_df = df[df["Attrition"]=="Yes"]
value_2 = new_df["MaritalStatus"].value_counts()
attrition_rate = np.floor((value_2/value_1)*100).values
sns.barplot(x=value_2.index, y=value_2.values,palette=["#11264e","#6faea4","#FEE08B","#D4A1E7","#E7A1A1"])
plt.title("Attrition Rate by MaritalStatus",
          fontweight="black",
          size=20,pad=20)
for index,value in enumerate(value_2):
    plt.text(index,value,str(value)+" ("+str(attrition_rate[index])+"% )",ha="center",va="bottom",
             size=15,fontweight="black")
plt.tight_layout()
plt.show()


#Visualization to show Employee Distribution by MonthlyIncome.
plt.figure(figsize=(13,6))
plt.subplot(1,2,1)
sns.histplot(x="MonthlyIncome", hue="Attrition", kde=True ,data=df,palette=["#11264e","#6faea4"])
plt.title("Employee Attrition by Monthly Income",fontweight="black",size=20,pad=15)

#Visualization to show Employee Attrition by Monthly Income.
plt.subplot(1,2,2)
sns.boxplot(x="Attrition",y="MonthlyIncome",data=df,palette=["#D4A1E7","#6faea4"])
plt.title("Employee Attrition by Monthly Income",fontweight="black",size=20,pad=15)
plt.tight_layout()
plt.show()


plt.figure(figsize=(13,6))
plt.subplot(1,2,1)
sns.histplot(x="MonthlyRate", hue="Attrition", data=df,kde=True, palette=["#11264e","#6faea4"])
plt.title("Employee Attrition by Monthly Rate",fontweight="black",size=20,pad=15)

plt.subplot(1,2,2)
sns.boxplot(x="Attrition",y="MonthlyRate",data=df,palette=["#D4A1E7","#6faea4"])
plt.title("Employee Attrition by Monthly Rate",fontweight="black",size=20,pad=15)
plt.tight_layout()
plt.show()


df["NumCompaniesWorked"].describe().T

count    1470.000000
mean        2.693197
std         2.498009
min         0.000000
25%         1.000000
50%         2.000000
75%         4.000000
max         9.000000
Name: NumCompaniesWorked, dtype: float64


# Define the bin edges for the groups
bin_edges = [0, 1, 3, 5, 10]

# Define the labels for the groups
bin_labels = ['0-1 Companies', '2-3 companies', '4-5 companies', "5+ companies"]

# Cut the DailyRate column into groups
df["NumCompaniesWorkedGroup"] = pd.cut(df['NumCompaniesWorked'], bins=bin_edges, labels=bin_labels)


#Visualization to show Total Employees by NumCompaniesWorked.
plt.figure(figsize=(13,6))
plt.subplot(1,2,1)
value_1 = df["NumCompaniesWorkedGroup"].value_counts()
plt.title("Employees by Companies Worked", fontweight="black", size=20, pad=20)
plt.pie(value_1.values, labels=value_1.index, autopct="%.1f%%",pctdistance=0.75,startangle=90,
        colors=['#FF6D8C', '#FF8C94', '#FFAC9B', '#FFCBA4'],textprops={"fontweight":"black","size":15})
center_circle = plt.Circle((0, 0), 0.4, fc='white')
fig = plt.gcf()
fig.gca().add_artist(center_circle)

    
#Visualization to show Attrition Rate by NumCompaniesWorked.
plt.subplot(1,2,2)
new_df = df[df["Attrition"]=="Yes"]
value_2 = new_df["NumCompaniesWorkedGroup"].value_counts()
attrition_rate = np.floor((value_2/value_1)*100).values
sns.barplot(x=value_2.index.tolist(), y=value_2.values,palette=["#11264e","#6faea4","#FEE08B","#D4A1E7","#E7A1A1"])
plt.title("Attrition Rate by Companies Worked",fontweight="black",size=20,pad=20)
for index,value in enumerate(value_2):
    plt.text(index,value,str(value)+" ("+str(int(attrition_rate[index]))+"%)",ha="center",va="bottom",
             size=15,fontweight="black")
plt.xticks(size=12)
plt.tight_layout()
plt.show()


#Visualization to show Total Employees by OverTime.
plt.figure(figsize=(15,6))
plt.subplot(1,2,1)
value_1 = df["OverTime"].value_counts()
plt.title("Employees by OverTime", fontweight="black", size=20, pad=20)
plt.pie(value_1.values, labels=value_1.index, autopct="%.1f%%",pctdistance=0.75,startangle=90,
        colors=["#ffb563","#FFC0CB"],textprops={"fontweight":"black","size":15})
center_circle = plt.Circle((0, 0), 0.4, fc='white')
fig = plt.gcf()
fig.gca().add_artist(center_circle)

    
#Visualization to show Attrition Rate by OverTime.
plt.subplot(1,2,2)
new_df = df[df["Attrition"]=="Yes"]
value_2 = new_df["OverTime"].value_counts()
attrition_rate = np.floor((value_2/value_1)*100).values
sns.barplot(x=value_2.index.tolist(), y=value_2.values,palette=["#D4A1E7","#E7A1A1"])
plt.title("Attrition Rate by OverTime",fontweight="black",size=20,pad=20)
for index,value in enumerate(value_2):
    plt.text(index,value,str(value)+" ("+str(int(attrition_rate[index]))+"%)",ha="center",va="bottom",
             size=15,fontweight="black")
plt.xticks(size=13)
plt.tight_layout()
plt.show()


#Visualization to show Employee Distribution by Percentage Salary Hike.
plt.figure(figsize=(16,6))
sns.countplot(x="PercentSalaryHike", hue="Attrition", data=df, palette=["green","brown"])
plt.title("Employee Attrition By PercentSalaryHike",fontweight="black",size=20,pad=15)
plt.show()


#Visualization to show Total Employees by PerformanceRating.
plt.figure(figsize=(14,6))
plt.subplot(1,2,1)
value_1 = df["PerformanceRating"].value_counts()
plt.title("Employees by PerformanceRating", fontweight="black", size=20, pad=20)
plt.pie(value_1.values, labels=value_1.index, autopct="%.1f%%",pctdistance=0.75,startangle=90,
        colors=["#ffb563","#FFC0CB"],textprops={"fontweight":"black","size":15})
center_circle = plt.Circle((0, 0), 0.4, fc='white')
fig = plt.gcf()
fig.gca().add_artist(center_circle)

    
#Visualization to show Attrition Rate by PerformanceRating.
plt.subplot(1,2,2)
new_df = df[df["Attrition"]=="Yes"]
value_2 = new_df["PerformanceRating"].value_counts()
attrition_rate = np.floor((value_2/value_1)*100).values
sns.barplot(x=value_2.index.tolist(),y= value_2.values,palette=["#D4A1E7","#E7A1A1"])
plt.title("Attrition Rate by PerformanceRating",fontweight="black",size=20,pad=20)
for index,value in enumerate(value_2):
    plt.text(index,value,str(value)+" ("+str(int(attrition_rate[index]))+"%)",ha="center",va="bottom",
             size=15,fontweight="black")
plt.tight_layout()
plt.show()


#Visualization to show Total Employees by RelationshipSatisfaction.
plt.figure(figsize=(13,6))
plt.subplot(1,2,1)
value_1 = df["RelationshipSatisfaction"].value_counts()
plt.title("Employees by RelationshipSatisfaction", fontweight="black", size=20, pad=20)
plt.pie(value_1.values, labels=value_1.index, autopct="%.1f%%",pctdistance=0.75,startangle=90,
        colors=['#6495ED', '#87CEEB', '#00BFFF', '#1E90FF'],textprops={"fontweight":"black","size":15})
center_circle = plt.Circle((0, 0), 0.4, fc='white')
fig = plt.gcf()
fig.gca().add_artist(center_circle)

    
#Visualization to show Attrition Rate by RelationshipSatisfaction.
plt.subplot(1,2,2)
new_df = df[df["Attrition"]=="Yes"]
value_2 = new_df["RelationshipSatisfaction"].value_counts()
attrition_rate = np.floor((value_2/value_1)*100).values
sns.barplot(x=value_2.index, y=value_2.values,order=value_2.index,palette=["#11264e","#6faea4","#FEE08B","#D4A1E7","#E7A1A1"])
plt.title("Attrition Rate by RelationshipSatisfaction",fontweight="black",size=20,pad=20)
for index,value in enumerate(value_2):
    plt.text(index,value,str(value)+" ("+str(int(attrition_rate[index]))+"%)",ha="center",va="bottom",
             size=15,fontweight="black")
plt.tight_layout()
plt.show()


##Visualization to show Total Employees by WorkLifeBalance.
plt.figure(figsize=(14.5,6))
plt.subplot(1,2,1)
value_1 = df["WorkLifeBalance"].value_counts()
plt.title("Employees by WorkLifeBalance", fontweight="black", size=20, pad=20)
plt.pie(value_1.values, labels=value_1.index, autopct="%.1f%%",pctdistance=0.75,startangle=90,
        colors= ['#FF8000', '#FF9933', '#FFB366', '#FFCC99'],textprops={"fontweight":"black","size":15})
center_circle = plt.Circle((0, 0), 0.4, fc='white')
fig = plt.gcf()
fig.gca().add_artist(center_circle)

#Visualization to show Attrition Rate by WorkLifeBalance.
plt.subplot(1,2,2)
new_df = df[df["Attrition"]=="Yes"]
value_2 = new_df["WorkLifeBalance"].value_counts()
attrition_rate = np.floor((value_2/value_1)*100).values
sns.barplot(x=value_2.index, y=value_2.values,order=value_2.index,palette=["#11264e","#6faea4","#FEE08B","#D4A1E7","#E7A1A1"])
plt.title("Employee Attrition Rate by WorkLifeBalance",fontweight="black",pad=15,size=18)
for index,value in enumerate(value_2.values):
    plt.text(index,value, str(value)+" ("+str(attrition_rate[index])+"%)",ha="center",va="bottom",
             fontweight="black",size=15)
plt.tight_layout()
plt.show()


# Define the bin edges for the groups
bin_edges = [0, 5, 10, 20, 50]

# Define the labels for the groups
bin_labels = ['0-5 years', '5-10 years', '10-20 years', "20+ years"]

# Cut the DailyRate column into groups
df["TotalWorkingYearsGroup"] = pd.cut(df['TotalWorkingYears'], bins=bin_edges, labels=bin_labels)


#Visualization to show Total Employees by TotalWorkingYearsGroup.
plt.figure(figsize=(14,6))
plt.subplot(1,2,1)
value_1 = df["TotalWorkingYearsGroup"].value_counts()
plt.title("Employees by TotalWorkingYears", fontweight="black", size=20, pad=20)
plt.pie(value_1.values, labels=value_1.index, autopct="%.1f%%",pctdistance=0.75,startangle=90,
        colors=['#E84040', '#E96060', '#E88181', '#E7A1A1'],textprops={"fontweight":"black","size":15})
center_circle = plt.Circle((0, 0), 0.4, fc='white')
fig = plt.gcf()
fig.gca().add_artist(center_circle)

    
#Visualization to show Attrition Rate by TotalWorkingYearsGroup.
plt.subplot(1,2,2)
new_df = df[df["Attrition"]=="Yes"]
value_2 = new_df["TotalWorkingYearsGroup"].value_counts()
attrition_rate = np.floor((value_2/value_1)*100).values
sns.barplot(x=value_2.index.tolist(), y=value_2.values,palette=["#11264e","#6faea4","#FEE08B","#D4A1E7","#E7A1A1"])
plt.title("Attrition Rate by TotalWorkingYears",fontweight="black",size=20,pad=20)
for index,value in enumerate(value_2):
    plt.text(index,value,str(value)+" ("+str(int(attrition_rate[index]))+"%)",ha="center",va="bottom",
             size=15,fontweight="black")
plt.tight_layout()
plt.show()


# Define the bin edges for the groups
bin_edges = [0, 1, 5, 10, 20]

# Define the labels for the groups
bin_labels = ['0-1 years', '2-5 years', '5-10 years', "10+ years"]

# Cut the DailyRate column into groups
df["YearsAtCompanyGroup"] = pd.cut(df['YearsAtCompany'], bins=bin_edges, labels=bin_labels)


#Visualization to show Total Employees by YearsAtCompanyGroup.
plt.figure(figsize=(14,6))
plt.subplot(1,2,1)
value_1 = df["YearsAtCompanyGroup"].value_counts()
plt.title("Employees by YearsAtCompany", fontweight="black", size=20, pad=20)
plt.pie(value_1.values, labels=value_1.index, autopct="%.1f%%",pctdistance=0.75,startangle=90,
        colors=['#FFB300', '#FFC300', '#FFD700', '#FFFF00'],textprops={"fontweight":"black","size":15})
center_circle = plt.Circle((0, 0), 0.4, fc='white')
fig = plt.gcf()
fig.gca().add_artist(center_circle)

    
#Visualization to show Attrition Rate by YearsAtCompanyGroup.
plt.subplot(1,2,2)
new_df = df[df["Attrition"]=="Yes"]
value_2 = new_df["YearsAtCompanyGroup"].value_counts()
attrition_rate = np.floor((value_2/value_1)*100).values
sns.barplot(x=value_2.index.tolist(), y=value_2.values,palette=["#11264e","#6faea4","#FEE08B","#D4A1E7","#E7A1A1"])
plt.title("Attrition Rate by YearsAtCompany",fontweight="black",size=20,pad=20)
for index,value in enumerate(value_2):
    plt.text(index,value,str(value)+" ("+str(int(attrition_rate[index]))+"%)",ha="center",va="bottom",
             size=15,fontweight="black")
plt.tight_layout()
plt.show()


# Define the bin edges for the groups
bin_edges = [0, 1, 5, 10, 20]

# Define the labels for the groups
bin_labels = ['0-1 years', '2-5 years', '5-10 years', "10+ years"]

# Cut the DailyRate column into groups
df["YearsInCurrentRoleGroup"] = pd.cut(df['YearsInCurrentRole'], bins=bin_edges, labels=bin_labels)


#Visualization to show Total Employees by YearsInCurrentRoleGroup.
plt.figure(figsize=(14,6))
plt.subplot(1,2,1)
value_1 = df["YearsInCurrentRoleGroup"].value_counts()
plt.title("Employees by YearsInCurrentRole", fontweight="black", size=20, pad=20)
plt.pie(value_1.values, labels=value_1.index, autopct="%.1f%%",pctdistance=0.75,startangle=90,
        colors=['#6495ED', '#87CEEB', '#00BFFF', '#1E90FF'],textprops={"fontweight":"black","size":15,"color":"black"})
center_circle = plt.Circle((0, 0), 0.4, fc='white')
fig = plt.gcf()
fig.gca().add_artist(center_circle)

    
#Visualization to show Attrition Rate by YearsInCurrentRoleGroup.
plt.subplot(1,2,2)
new_df = df[df["Attrition"]=="Yes"]
value_2 = new_df["YearsInCurrentRoleGroup"].value_counts()
attrition_rate = np.floor((value_2/value_1)*100).values
sns.barplot(x=value_2.index.tolist(), y=value_2.values,palette= ["orange","green","yellow","blue","brown"])
plt.title("Attrition Rate by YearsInCurrentRole",fontweight="black",size=20,pad=20)
for index,value in enumerate(value_2):
    plt.text(index,value,str(value)+" ("+str(int(attrition_rate[index]))+"%)",ha="center",va="bottom",
             size=15,fontweight="black")
plt.tight_layout()
plt.show()


# Define the bin edges for the groups
bin_edges = [0, 1, 5, 10, 20]

# Define the labels for the groups
bin_labels = ['0-1 years', '2-5 years', '5-10 years', "10+ years"]

# Cut the DailyRate column into groups
df["YearsSinceLastPromotionGroup"] = pd.cut(df['YearsSinceLastPromotion'], bins=bin_edges, labels=bin_labels)


#Visualization to show Total Employees by YearsSinceLastPromotionGroup.
plt.figure(figsize=(14,6))
plt.subplot(1,2,1)
value_1 = df["YearsSinceLastPromotionGroup"].value_counts()
plt.title("Employees by YearsSinceLastPromotion", fontweight="black", size=20, pad=20)
plt.pie(value_1.values, labels=value_1.index, autopct="%.1f%%",pctdistance=0.75,startangle=90,
        colors=['#FF6D8C', '#FF8C94', '#FFAC9B', '#FFCBA4'],textprops={"fontweight":"black","size":15})
center_circle = plt.Circle((0, 0), 0.4, fc='white')
fig = plt.gcf()
fig.gca().add_artist(center_circle)

    
#Visualization to show Attrition Rate by YearsSinceLastPromotionGroup.
plt.subplot(1,2,2)
new_df = df[df["Attrition"]=="Yes"]
value_2 = new_df["YearsSinceLastPromotionGroup"].value_counts()
attrition_rate = np.floor((value_2/value_1)*100).values
sns.barplot(x=value_2.index.tolist(), y=value_2.values,palette=["#11264e","#6faea4","#FEE08B","#D4A1E7","#E7A1A1"])

plt.title("Attrition Rate by YearsSinceLastPromotion",fontweight="black",size=20,pad=20)
for index,value in enumerate(value_2):
    plt.text(index,value,str(value)+" ("+str(int(attrition_rate[index]))+"%)",ha="center",va="bottom",
             size=15,fontweight="black")
plt.tight_layout()
plt.show()


# Define the bin edges for the groups
bin_edges = [0, 1, 5, 10, 20]

# Define the labels for the groups
bin_labels = ['0-1 years', '2-5 years', '5-10 years', "10+ years"]

# Cut the DailyRate column into groups
df["YearsWithCurrManagerGroup"] = pd.cut(df['YearsWithCurrManager'], bins=bin_edges, labels=bin_labels)


#Visualization to show Total Employees by YearsWithCurrManagerGroup.
plt.figure(figsize=(14,6))
plt.subplot(1,2,1)
value_1 = df["YearsWithCurrManagerGroup"].value_counts()
plt.title("Employees by YearsWithCurrManager", fontweight="black", size=20, pad=20)
plt.pie(value_1.values, labels=value_1.index, autopct="%.1f%%",pctdistance=0.75,startangle=90,
        colors= ['#FF8000', '#FF9933', '#FFB366', '#FFCC99'],textprops={"fontweight":"black","size":15})
center_circle = plt.Circle((0, 0), 0.4, fc='white')
fig = plt.gcf()
fig.gca().add_artist(center_circle)

    
#Visualization to show Attrition Rate by YearsWithCurrManagerGroup.
plt.subplot(1,2,2)
new_df = df[df["Attrition"]=="Yes"]
value_2 = new_df["YearsWithCurrManagerGroup"].value_counts()
attrition_rate = np.floor((value_2/value_1)*100).values
sns.barplot(x=value_2.index.tolist(), y=value_2.values,palette=["#11264e","#6faea4","#FEE08B","#D4A1E7","#E7A1A1"])
plt.title("Attrition Rate by YearsWithCurrManager",fontweight="black",size=20,pad=20)
for index,value in enumerate(value_2):
    plt.text(index,value,str(value)+" ("+str(int(attrition_rate[index]))+"%)",ha="center",va="bottom",
             size=15,fontweight="black")
plt.tight_layout()
plt.show()


import numpy as np
df = pd.read_csv(r'C:\Users\Admin\Desktop\IBM\Data\WA_Fn-UseC_-HR-Employee-Attrition.csv')
num_cols = df.select_dtypes(np.number).columns


new_df = df.copy()

new_df["Attrition"] = new_df["Attrition"].replace({"No":0,"Yes":1})


import pandas as pd
from scipy import stats

f_scores = {}
p_values = {}

for column in num_cols:
    f_score, p_value = stats.f_oneway(new_df[column], new_df["Attrition"])
    
    f_scores[column] = f_score
    p_values[column] = p_value


f_scores = {}
p_values = {}

for column in num_cols:
    f_score, p_value = stats.f_oneway(new_df[column],new_df["Attrition"])
    
    f_scores[column] = f_score
    p_values[column] = p_value

Number of variables	32
Number of observations	1470
Missing cells	0
Missing cells (%)	0.0%
Duplicate rows	0
Duplicate rows (%)	0.0%
Total size in memory	367.6 KiB
Average record size in memory	256.1 B

Numeric	15
Boolean	2
Categorical	15

`Age` is highly overall correlated with `TotalWorkingYears`	High correlation
`MonthlyIncome` is highly overall correlated with `TotalWorkingYears` and 1 other fields	High correlation
`PercentSalaryHike` is highly overall correlated with `PerformanceRating`	High correlation
`TotalWorkingYears` is highly overall correlated with `Age` and 4 other fields	High correlation
`YearsAtCompany` is highly overall correlated with `TotalWorkingYears` and 4 other fields	High correlation
`YearsInCurrentRole` is highly overall correlated with `YearsAtCompany` and 3 other fields	High correlation
`YearsSinceLastPromotion` is highly overall correlated with `YearsAtCompany` and 2 other fields	High correlation
`YearsWithCurrManager` is highly overall correlated with `YearsAtCompany` and 2 other fields	High correlation
`Fecha` is highly overall correlated with `TotalWorkingYears` and 4 other fields	High correlation
`Department` is highly overall correlated with `EducationField` and 1 other fields	High correlation
`EducationField` is highly overall correlated with `Department`	High correlation
`JobLevel` is highly overall correlated with `MonthlyIncome` and 2 other fields	High correlation
`JobRole` is highly overall correlated with `Department` and 1 other fields	High correlation
`MaritalStatus` is highly overall correlated with `StockOptionLevel`	High correlation
`PerformanceRating` is highly overall correlated with `PercentSalaryHike`	High correlation
`StockOptionLevel` is highly overall correlated with `MaritalStatus`	High correlation
`NumCompaniesWorked` has 197 (13.4%) zeros	Zeros
`TrainingTimesLastYear` has 54 (3.7%) zeros	Zeros
`YearsAtCompany` has 44 (3.0%) zeros	Zeros
`YearsInCurrentRole` has 244 (16.6%) zeros	Zeros
`YearsSinceLastPromotion` has 581 (39.5%) zeros	Zeros
`YearsWithCurrManager` has 263 (17.9%) zeros	Zeros

Analysis started	2023-07-13 23:11:34.002046
Analysis finished	2023-07-13 23:12:36.899185
Duration	1 minute and 2.9 seconds
Software version	pandas-profiling v3.6.6
Download configuration	config.json

Distinct	43
Distinct (%)	2.9%
Missing	0
Missing (%)	0.0%
Infinite	0
Infinite (%)	0.0%
Mean	36.92381

	Age	Attrition	BusinessTravel	DailyRate	Department	DistanceFromHome	Education	EducationField	EmployeeCount	EmployeeNumber	EnvironmentSatisfaction	Gender	HourlyRate	JobInvolvement	JobLevel	JobRole	JobSatisfaction	MaritalStatus	MonthlyIncome	MonthlyRate	NumCompaniesWorked	Over18	OverTime	PercentSalaryHike	PerformanceRating	RelationshipSatisfaction	StandardHours	StockOptionLevel	TotalWorkingYears	TrainingTimesLastYear	WorkLifeBalance	YearsAtCompany	YearsInCurrentRole	YearsSinceLastPromotion	YearsWithCurrManager
0	41	Yes	Travel_Rarely	1102	Sales	1	2	Life Sciences	1	1	2	Female	94	3	2	Sales Executive	4	Single	5993	19479	8	Y	Yes	11	3	1	80	0	8	0	1	6	4	0	5
1	49	No	Travel_Frequently	279	Research & Development	8	1	Life Sciences	1	2	3	Male	61	2	2	Research Scientist	2	Married	5130	24907	1	Y	No	23	4	4	80	1	10	3	3	10	7	1	7
2	37	Yes	Travel_Rarely	1373	Research & Development	2	2	Other	1	4	4	Male	92	2	1	Laboratory Technician	3	Single	2090	2396	6	Y	Yes	15	3	2	80	0	7	3	3	0	0	0	0
3	33	No	Travel_Frequently	1392	Research & Development	3	4	Life Sciences	1	5	4	Female	56	3	1	Research Scientist	3	Married	2909	23159	1	Y	Yes	11	3	3	80	0	8	3	3	8	7	3	0
4	27	No	Travel_Rarely	591	Research & Development	2	1	Medical	1	7	1	Male	40	3	1	Laboratory Technician	2	Married	3468	16632	9	Y	No	12	3	4	80	1	6	3	3	2	2	2	2

STT	Attribute Name	Meaning
1	Age	Employee's age
2	Gender	Employee's Gender
3	BusinessTravel	Frequency of employees' business trips
4	DailyRate	Daily salary rate for employees
5	Department	Office of employees
6	DistanceFromHome	Distance from home in miles to work
7	Education	Level of education achieved by staff
8	EducationField	Employee's field of study
9	EmployeeCount	Total number of employees in the organization
10	EmployeeNumber	A unique identifier for each employee record
11	EnvironmentSatisfaction	Employee satisfaction with their working environment
12	HourlyRate	Hourly rate for employees
13	JobInvolvement	Level of involvement required for the employee's job
14	JobLevel	Employee's level of work
15	JobRole	The role of employees in the organization
16	JobSatisfaction	Employee satisfaction with their work
17	MaritalStatus	Employee's marital status
18	MonthlyIncome	Employee's monthly income
19	MonthlyRate	Monthly salary rate for employees
20	NumCompaniesWorked	Number of companies the employee worked for
21	Over18	Whether the employee is over 18 years old
22	OverTime	Do employees work overtime
23	PercentSalaryHike	Salary increase rate for employees
24	PerformanceRating	The performance rating of the employee
25	RelationshipSatisfaction	Employee satisfaction with their relationships
26	StandardHours	Standard working hours for employees
27	StockOptionLevel	Employee stock option level
28	TotalWorkingYears	Total number of years the employee has worked
29	TrainingTimesLastYear	Number of times employees were taken to training in the last year
30	WorkLifeBalance	Employees' perception of their work-life balance
31	YearsAtCompany	Number of years employees have been with the company
32	YearsInCurrentRole	Number of years the employee has been in their current role
33	YearsSinceLastPromotion	Number of years since employee's last promotion
34	YearsWithCurrManager	Number of years an employee has been with their current manager
35	Attrition	Does the employee leave the organization

	Age	DailyRate	DistanceFromHome	Education	EmployeeCount	EmployeeNumber	EnvironmentSatisfaction	HourlyRate	JobInvolvement	JobLevel	JobSatisfaction	MonthlyIncome	MonthlyRate	NumCompaniesWorked	PercentSalaryHike	PerformanceRating	RelationshipSatisfaction	StandardHours	StockOptionLevel	TotalWorkingYears	TrainingTimesLastYear	WorkLifeBalance	YearsAtCompany	YearsInCurrentRole	YearsSinceLastPromotion	YearsWithCurrManager
333	43	1001	7	3	1	451	3	43	3	3	1	9985	9262	8	16	3	1	80	1	10	1	2	1	0	0	0
644	31	1222	11	4	1	895	4	48	3	1	4	2356	14871	3	19	3	2	80	1	8	2	3	6	4	0	2
870	35	1361	17	4	1	1218	3	94	3	2	1	8966	21026	3	15	3	4	80	3	15	2	3	7	7	1	7
1422	35	1490	11	4	1	2003	4	43	3	1	3	2660	20232	7	11	3	3	80	1	5	3	3	2	2	2	2
1194	47	1225	2	4	1	1676	2	47	4	4	2	15972	21086	6	14	3	3	80	3	29	2	3	3	2	1	2

	Attrition	BusinessTravel	Department	Education	EducationField	EnvironmentSatisfaction	Gender	JobInvolvement	JobLevel	JobRole	JobSatisfaction	MaritalStatus	Over18	OverTime	PerformanceRating	RelationshipSatisfaction	WorkLifeBalance
906	No	Travel_Rarely	Research & Development	Bachelor	Technical Degree	High	Female	Very High	Entry Level	Research Scientist	High	Married	Y	No	Excellent	Very High	Good
518	No	Travel_Rarely	Sales	Master	Marketing	Very High	Female	Medium	Junior Level	Sales Executive	Very High	Single	Y	No	Outstanding	Low	Better
1385	No	Travel_Rarely	Sales	Master	Medical	Very High	Male	High	Mid Level	Sales Executive	High	Divorced	Y	No	Excellent	High	Good
470	No	Travel_Frequently	Sales	Bachelor	Medical	Very High	Male	High	Entry Level	Sales Representative	Very High	Married	Y	No	Excellent	High	Better
1055	No	Travel_Frequently	Research & Development	Bachelor	Medical	Medium	Male	High	Senior Level	Research Director	Low	Divorced	Y	No	Excellent	Very High	Good

	count	mean	std	min	25%	50%	75%	max
Age	1470.0	36.923810	9.135373	18.0	30.00	36.0	43.00	60.0
DailyRate	1470.0	802.485714	403.509100	102.0	465.00	802.0	1157.00	1499.0
DistanceFromHome	1470.0	9.192517	8.106864	1.0	2.00	7.0	14.00	29.0
EmployeeCount	1470.0	1.000000	0.000000	1.0	1.00	1.0	1.00	1.0
EmployeeNumber	1470.0	1024.865306	602.024335	1.0	491.25	1020.5	1555.75	2068.0
HourlyRate	1470.0	65.891156	20.329428	30.0	48.00	66.0	83.75	100.0
MonthlyIncome	1470.0	6502.931293	4707.956783	1009.0	2911.00	4919.0	8379.00	19999.0
MonthlyRate	1470.0	14313.103401	7117.786044	2094.0	8047.00	14235.5	20461.50	26999.0
NumCompaniesWorked	1470.0	2.693197	2.498009	0.0	1.00	2.0	4.00	9.0
PercentSalaryHike	1470.0	15.209524	3.659938	11.0	12.00	14.0	18.00	25.0
StandardHours	1470.0	80.000000	0.000000	80.0	80.00	80.0	80.00	80.0
StockOptionLevel	1470.0	0.793878	0.852077	0.0	0.00	1.0	1.00	3.0
TotalWorkingYears	1470.0	11.279592	7.780782	0.0	6.00	10.0	15.00	40.0
TrainingTimesLastYear	1470.0	2.799320	1.289271	0.0	2.00	3.0	3.00	6.0
YearsAtCompany	1470.0	7.008163	6.126525	0.0	3.00	5.0	9.00	40.0
YearsInCurrentRole	1470.0	4.229252	3.623137	0.0	2.00	3.0	7.00	18.0
YearsSinceLastPromotion	1470.0	2.187755	3.222430	0.0	0.00	1.0	3.00	15.0
YearsWithCurrManager	1470.0	4.123129	3.568136	0.0	2.00	3.0	7.00	17.0

	count	unique	top	freq
Attrition	1470	2	No	1233
BusinessTravel	1470	3	Travel_Rarely	1043
Department	1470	3	Research & Development	961
Education	1470	5	Bachelor	572
EducationField	1470	6	Life Sciences	606
EnvironmentSatisfaction	1470	4	High	453
Gender	1470	2	Male	882
JobInvolvement	1470	4	High	868
JobLevel	1470	5	Entry Level	543
JobRole	1470	9	Sales Executive	326
JobSatisfaction	1470	4	Very High	459
MaritalStatus	1470	3	Married	673
OverTime	1470	2	No	1054
PerformanceRating	1470	2	Excellent	1244
RelationshipSatisfaction	1470	4	High	459
WorkLifeBalance	1470	4	Better	893

Minimum	18
Maximum	60
Zeros	0
Zeros (%)	0.0%
Negative	0
Negative (%)	0.0%
Memory size	11.6 KiB

Minimum	18
5-th percentile	24
Q1	30
median	36
Q3	43
95-th percentile	54
Maximum	60
Range	42
Interquartile range (IQR)	13

Standard deviation	9.1353735
Coefficient of variation (CV)	0.24741146
Kurtosis	-0.40414514
Mean	36.92381
Median Absolute Deviation (MAD)	6
Skewness	0.4132863
Sum	54278
Variance	83.455049
Monotonicity	Not monotonic

Value	Count	Frequency (%)
35	78	5.3%
34	77	5.2%
36	69	4.7%
31	69	4.7%
29	68	4.6%
32	61	4.1%
30	60	4.1%
33	58	3.9%
38	58	3.9%
40	57	3.9%
Other values (33)	815	55.4%

Value	Count	Frequency (%)
18	8	0.5%
19	9	0.6%
20	11	0.7%
21	13	0.9%
22	16	1.1%
23	14	1.0%
24	26	1.8%
25	26	1.8%
26	39	2.7%
27	48	3.3%

Value	Count	Frequency (%)
60	5	0.3%
59	10	0.7%
58	14	1.0%
57	4	0.3%
56	14	1.0%
55	22	1.5%
54	18	1.2%
53	19	1.3%
52	18	1.2%
51	19	1.3%

False	1233
True	237

Travel_Rarely	1043
Travel_Frequently	277
Non-Travel	150

Distinct	2
Distinct (%)	0.1%
Missing	0
Missing (%)	0.0%
Memory size	1.6 KiB

Distinct	3
Distinct (%)	0.2%
Missing	0
Missing (%)	0.0%
Memory size	11.6 KiB

Total characters	19768
Distinct characters	17
Distinct categories	4 ?
Distinct scripts	2 ?
Distinct blocks	1 ?

1st row	Travel_Rarely
2nd row	Travel_Frequently
3rd row	Travel_Rarely
4th row	Travel_Frequently
5th row	Travel_Rarely

Distinct	886
Distinct (%)	60.3%
Missing	0
Missing (%)	0.0%
Infinite	0
Infinite (%)	0.0%
Mean	802.48571

Minimum	102
Maximum	1499
Zeros	0
Zeros (%)	0.0%
Negative	0
Negative (%)	0.0%
Memory size	11.6 KiB

Minimum	102
5-th percentile	165.35
Q1	465
median	802
Q3	1157
95-th percentile	1424.1
Maximum	1499
Range	1397
Interquartile range (IQR)	692

Standard deviation	403.5091
Coefficient of variation (CV)	0.50282403
Kurtosis	-1.2038228
Mean	802.48571
Median Absolute Deviation (MAD)	344
Skewness	-0.0035185684
Sum	1179654
Variance	162819.59
Monotonicity	Not monotonic

Total characters	24317
Distinct characters	20
Distinct categories	4 ?
Distinct scripts	2 ?
Distinct blocks	1 ?

Distinct	29
Distinct (%)	2.0%
Missing	0
Missing (%)	0.0%
Infinite	0
Infinite (%)	0.0%
Mean	9.192517

IBM HR Analytics Employee Attrition¶

Autores: Tamara, Jorge Luis Arias Otero, Diana, Andres, Aristides.🖋️

Análisis de datos sobre el conjunto de datos de rotación de los trabajadores¶

Objetivo:

El objetivo principal es comprender los factores que contribuyen a la rotación de empleados en una empresa y desarrollar un modelo predictivo para predecir la Attrition.¶

Realizar una exploración inicial del conjunto de datos para comprender su estructura, variables y distribución.¶

Realizar exploración inicial del conjunto de datos¶

Descripción de las columnas del Dataset ¶

1. Calculando la dimensión del Dataset.¶

2. Generación de Información Básica de Atributos.¶

💬 Conclusion:

Muestra aleatoria del conjunto de datos con solo características numéricas.¶

💬 Conclusion:

4. Etiquetado de Categorías en Características Numéricas.¶

Mostrando una muestra aleatoria de conjunto de datos con solo características categóricas.¶

Comprobar si hay registros duplicados.¶

💬 Conclusion:

Calcular el número total de valores nulos y el porcentaje de valores nulos.¶

Realización de análisis descriptivos de atributos numéricos.¶

💬 Nota:

💬 Conclusion:

Eliminación de columnas, lo que no implica ningún conocimiento significativo en nuestro análisis.¶

Realización de análisis descriptivos sobre las caracteristicas categóricas.¶

💬 Nota:

💬 Conclusion:

Comprobación de valores únicos de columnas categóricas.¶

💬 Conclusion:

Analysis Exploratorio de los Datos.¶

Visualización de la tasa de deserción de empleados.¶

💬 Conclusion:

Creamos la columna Fecha y se agreguará al archivo CSV original.¶

Para Analizar aun mas la Attrition de la empresa y tener mejores resultados¶

Generar el informe de perfilado de datos .¶

Pandas Profiling¶

Overview

Variables

Common Values

Length

Common Values (Plot)

Most occurring characters

Most occurring categories

Most frequent character per category

Lowercase Letter

Uppercase Letter

Connector Punctuation

Dash Punctuation

Most occurring scripts

Most frequent character per script

Latin

Common

Most occurring blocks

Most frequent character per block

ASCII

Common Values

Length

Common Values (Plot)

Most occurring characters

Most occurring categories

Most frequent character per category

Lowercase Letter

Uppercase Letter

Space Separator

Other Punctuation

Most occurring scripts

Most frequent character per script

Latin

Common

Most occurring blocks

Most frequent character per block

ASCII

Common Values

Length

Common Values (Plot)

Most occurring characters

Most occurring categories

Most frequent character per category

Decimal Number

Most occurring scripts

Most frequent character per script

Common

IBM HR Analytics Employee Attrition
¶

Análisis de datos sobre el conjunto de datos de rotación de los trabajadores
¶

Descripción de las columnas del Dataset
¶

Analysis Exploratorio de los Datos.
¶

Visualización de la tasa de deserción de empleados.
¶

Creamos la columna Fecha y se agreguará al archivo CSV original.
¶

Generar el informe de perfilado de datos .
¶

Standard deviation	8.1068644
Coefficient of variation (CV)	0.88189823
Kurtosis	-0.2248334
Mean	9.192517
Median Absolute Deviation (MAD)	5
Skewness	0.958118
Sum	13513
Variance	65.721251
Monotonicity	Not monotonic

Distinct	6
Distinct (%)	0.4%
Missing	0
Missing (%)	0.0%
Memory size	11.6 KiB

Total characters	15484
Distinct characters	26
Distinct categories	3 ?
Distinct scripts	2 ?
Distinct blocks	1 ?

Total characters	7056
Distinct characters	6
Distinct categories	2 ?
Distinct scripts	1 ?
Distinct blocks	1 ?

Distinct	71
Distinct (%)	4.8%
Missing	0
Missing (%)	0.0%
Infinite	0
Infinite (%)	0.0%
Mean	65.891156

Total characters	26564
Distinct characters	29
Distinct categories	3 ?
Distinct scripts	2 ?
Distinct blocks	1 ?

Total characters	10147
Distinct characters	14
Distinct categories	2 ?
Distinct scripts	1 ?
Distinct blocks	1 ?

Distinct	1349
Distinct (%)	91.8%
Missing	0
Missing (%)	0.0%
Infinite	0
Infinite (%)	0.0%
Mean	6502.9313

Minimum	1009
Maximum	19999
Zeros	0
Zeros (%)	0.0%
Negative	0
Negative (%)	0.0%
Memory size	11.6 KiB

Standard deviation	4707.9568
Coefficient of variation (CV)	0.72397455
Kurtosis	1.0052327
Mean	6502.9313
Median Absolute Deviation (MAD)	2199
Skewness	1.3698167
Sum	9559309
Variance	22164857
Monotonicity	Not monotonic